Lars Moelleken voku

You are a system designed to extract meaningful LLM prompting patterns from chat histories. Analyze the full conversation history as defined below and identify:

Frequently repeated LLM prompt behaviors
Their function
Contextual usage — where in the conversation this pattern appears, and why
Underlying principle — the deeper design thinking or learning theory implied

Mastering LLM Prompts and Code Optimization: Practical Techniques for Developers

Optimizing inputs for LLMs ensures better, more consistent outputs while leveraging the full potential of the model's underlying capabilities. By understanding core concepts like tokenization, embeddings, self-attention, and context limits, you can tailor inputs to achieve desired outcomes reliably. Below, you'll find fundamental techniques and best practices organized into practical strategies.

🎯 1. Controlling Probabilities: Guide Model Outputs

🧠 Theory: LLMs always follow probabilities when generating text. For every token, the model calculates a probability distribution based on the context provided. By carefully structuring inputs or presenting examples, we can shift the probabilities toward the desired outcome:

Codelight Manifesto

Tip: AI Copilot that follows this document: https://chatgpt.com/g/g-6737e2027dbc8191a00c2a73abf7907e-codelight

Why We Need the Codelight Manifesto

Imagine building a house without standardized measurements for doors or windows. Every house would need custom furniture, and moving between homes would feel like solving a puzzle. Software development in many ways is still in this stage of chaos—a "wild west" era where the lack of universal principles often leads to inefficiencies, miscommunication, and brittle systems.

Take this example:

Code is clean if it can be understood easily – by everyone on the team. Clean code can be read and enhanced by a developer other than its original author. With understandability comes readability, changeability, extensibility and maintainability.

General rules

Follow standard conventions.
Keep it simple stupid. Simpler is always better. Reduce complexity as much as possible.
Boy scout rule. Leave the campground cleaner than you found it.
Always find root cause. Always look for the root cause of a problem.

Design rules

Live-Version:

https://chatgpt.com/g/g-g1905v3LQ-php-copilot

Custom Instruction:

{
 "personality": "This GPT, responds as experienced senior PHP developer and architect Lars Moelleken from github.com/voku and ALWAYS applies a combination of `Sync_Process_Collaborative_Workflow.md` and `Workflow-Framework` as extendable workflow. He writes modern, strict PHP code with specific types and PHPDoc annotations, focusing on readability and precision to support static code analysis and maintainable systems: `CODING_MANIFEST.md`. All code includes specific PHPDoc annotations for e.g. array types, int-ranges, Generics, Generator, and conditional types, or when type hints alone don’t convey full intent; PhpDoc includes e.g. generics (`@template TValue`, `@extends AbstractValueObject`, `@implements Rule`), class-strings (`class-string`), arrays (`list`, `array`, `non-empty-list`), array-shapes (`array{foo?

	<?php

	// ⏱️ v1 \| Simple, automatic timeout with default polling interval
	timeoutForEach(5, range(1, 3), static fn (int $value) => doThing());

	// ⏱️ v2 \| Simple, automatic timeout with default polling interval
	$upper = timeoutMap(0.5, ['alice', 'bob', 'charlie'], static fn ($name) => strtoupper($name));
	//\PHPStan\dumpType($upper); // Dumped type: list<uppercase-string>

	// 👁️ Timeout-aware loop, low CPU overhead

	{
	"name": "SYNC: Iterative Agent-Based Execution (v1.2.0)",
	"description": "A rigorous, agent-driven framework for complex, iterative software development, optimized for LLM execution. It emphasizes verifiable data, objective analysis, and robust, self-correcting outcomes across multiple cycles of refinement. By leveraging specialized AI agents and pattern-based knowledge synthesis, it enhances security, developer experience (DX), and clarity. This framework proactively addresses LLM 'blind spots' through enforced phase structures, mandate-verified checkpoints, and integrated human-in-the-loop control.",
	"version": "1.2.0",
	"semver": true,
	"sources": {
	"1": "https://arxiv.org/abs/2305.10601 — Reflexion: Language Models Reflecting on Their Own Outputs Improve Reasoning",
	"2": "https://arxiv.org/abs/2302.04761 — Tree of Thoughts: Deliberate Problem Solving with Large Language Models",
	"3": "https://arxiv.org/abs/2303.09016 — Self-Refine: Iterative Refinement with Self-Feedback",
	"4": "

	<?php

	declare(strict_types=1);

	require_once __DIR__ . '/AbstractFixerHelper.php';

	use PhpCsFixer\Tokenizer\Tokens;
	use PhpCsFixer\Tokenizer\Token;
	use PhpCsFixer\Tokenizer\Analyzer\FunctionsAnalyzer;

	#!/usr/bin/php
	<?php

	$output = [];
	exec('[ -n "$SSH_CLIENT" ] \|\| [ -n "$SSH_TTY" ] && echo "remote" \|\| echo "local"', $output);
	if ($output[0] != 'local') {
	echo "Run this script only on your computer!\n\n";
	// @codingStandardsIgnoreStart
	exit(1);
	// @codingS

	<?php

	use PHP_CodeSniffer\Files\File;
	use PHP_CodeSniffer\Sniffs\Sniff;

	final class VdmgReturnIntValueCheckSniff implements Sniff {

	/**
	* String representation of error.
	*